Smart Internet of Things Projects

Building a tracking vision system for moving objects

In this section, we build a simple tacking vision system. We already learned how to detect a face in an image. Now we try to detect faces on video.

The idea is simple. We change a still image as source to a frame image from a camera. After calling read() from the VideoCapture object, we pass the frame image into face_cascade.detectMultiScale(). Then, we show it a picture dialog. That's it.

For implementation, type these scripts:

import numpy as np import cv2 face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml') cap = cv2.VideoCapture(0) while True: # Capture frame-by-frame ret, frame = cap.read() gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY) faces = face_cascade.detectMultiScale(gray, ...